# EditSleuth: A Dataset of Grounded Reasoning Chains for Image-Edit Forensics

arXiv: https://arxiv.org/abs/2605.08695 · HTML: https://mlsanity.com/paper/2605.08695/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 9 May 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 26 of 26)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing](https://mlsanity.com/paper/2306.10012/) (2023)
- [DIRE for Diffusion-Generated Image Detection](https://mlsanity.com/paper/2303.09295/) (2023)
- [Emu Edit: Precise Image Editing via Recognition and Generation Tasks](https://mlsanity.com/paper/2311.10089/) (2023)
- [Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2403.16999/) (2024)
- [UltraEdit: Instruction-based Fine-Grained Image Editing at Scale](https://mlsanity.com/paper/2407.05282/) (2024)
- [HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing](https://mlsanity.com/paper/2404.09990/) (2024)
- [Improve Vision Language Model Chain-of-thought Reasoning](https://mlsanity.com/paper/2410.16198/) (2024)
- [M3CoT: A Novel Benchmark for Multi-Domain Multi-step Multi-modal Chain-of-Thought](https://mlsanity.com/paper/2405.16473/) (2024)
- [FakeShield: Explainable Image Forgery Detection and Localization via Multi-modal Large Language Models](https://mlsanity.com/paper/2410.02761/) (2024)
- [SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model](https://mlsanity.com/paper/2412.04292/) (2024)
- [Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation](https://mlsanity.com/paper/2503.14905/) (2025)
- [LEGION: Learning to Ground and Explain for Synthetic Image Detection](https://mlsanity.com/paper/2503.15264/) (2025)
- [AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors](https://mlsanity.com/paper/2310.17419/) (2023)
- [Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing](https://mlsanity.com/paper/2510.19808/) (2025)
- [LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models](https://mlsanity.com/paper/2410.09732/) (2024)
- [Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector](https://mlsanity.com/paper/2503.20188/) (2025)
- [Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detection](https://mlsanity.com/paper/2602.10042/) (2026)
- [Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs](https://mlsanity.com/paper/2511.08409/) (2025)
- [VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection](https://mlsanity.com/paper/2604.13660/) (2026)

## Built on by (most cited first, 1 of 1)

- [Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them](https://mlsanity.com/paper/2609.32763/) (2026)

## Abstract (arXiv)

Forensic analysis of AI-edited images requires more than binary real-versus-fake prediction: a useful system should localize the edit, identify its semantic type, and ground its decisions in visual evidence. Existing image-forensics datasets typically emphasize detection or localization, while reasoning-supervised vision-language datasets rarely target image manipulation and often rely on LLM-generated rationales whose faithfulness is difficult to verify. We introduce EditSleuth, a dataset of 257,725 image-edit triplets constructed from existing image-editing corpora for grounded image-edit forensic reasoning. Each example includes an edited image, its source image, a binary edit mask, a 12-class edit taxonomy label, a difficulty score, and a six-step reasoning chain. EditSleuth chains are generated deterministically from triplet-grounded upstream artifacts, with each statement tied to a specific computable source of evidence. Our analysis reveals that a naive four-component difficulty formulation suffers from a rank-2 correlation collapse among magnitude features; a simplified three-component formulation substantially increases score dispersion on both Pico-Banana and MagicBrush. Difficulty also varies meaningfully within most edit categories, indicating that the score is not a proxy for edit type. As an initial learning study, we fine-tune Qwen2-VL-2B with LoRA and find that chain-as-target supervision matches a label-only baseline on classification accuracy among parseable answers, while additionally yielding grounded explanatory prose that label-only supervision cannot produce. We release the dataset, the deterministic construction pipeline, and pilot training scripts.